-
Notifications
You must be signed in to change notification settings - Fork 54
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
code details #6
Comments
Hi, thanks for interested in my work. Sorry for missing the pre-preprocessing code and data. (I left my previous lab and forgot to backup) I try to clarify your problems here
|
thank you for your reply!!! |
thank you for your reply!!!
来自 Outlook<http://aka.ms/weboutlook>
…________________________________
发件人: Tsu-Jui Fu <notifications@github.com>
发送时间: 2019年9月18日 14:53
收件人: tsujuifu/pytorch_graph-rel <pytorch_graph-rel@noreply.github.com>
抄送: niartnelis <daiminjiang@outlook.com>; Author <author@noreply.github.com>
主题: Re: [tsujuifu/pytorch_graph-rel] code details (#6)
Hi, thanks for interested in my work.
Sorry for missing the pre-preprocessing code and data. (I left my previous lab and forgot to backup)
I will reproduce and update it later. (since I just start my PhD and it's quite busy these days, maybe after CVPR or ACL)
Hence, I try to clarify your problems here
1. for idx, inp, pos, dep_fw, dep_bw, ans_ne, wgt_ne, ans_rel, wgt_rel in ld_ts
BS: batch_size
SL: sentence_length
ED: embedding_dimension
idx: not so important, you can just ignore it
inp: the input sentence ([BS, SL, ED])
pos: the part-of-speech tag of each word ([BS, SL])
dep_fw: the dependencty adjacency matrix (forward edge) of each word-pair ([BS, SL, SL])
dep_bw: the dependencty adjacency matrix (backward edge) of each word-pair ([BS, SL, SL])
ans_ne, ans_rel: the output tag of name entity of each word and relation of each word-pair ([BS, SL] ans [BS, SL, SL])
wgt_ne, wgt_rel: the loss weight of name entity of each word and relation of each word-pair, 1 for those contains name entity or relation, otherwise 0 ([BS, SL], [BS, SL, SL])
1. pos is the part-of-speech tag of each word and it's from spaCy<https://spacy.io/usage/linguistic-features#pos-tagging>
2. the dependency parsing also comes from spaCy<https://spacy.io/usage/linguistic-features#dependency-parse> (please notice that there can be forward and backward edges of the dependency tree)
―
You are receiving this because you authored the thread.
Reply to this email directly, view it on GitHub<#6?email_source=notifications&email_token=AI47XMFCVUDYQQOKR6ANH73QKHF5HA5CNFSM4IXXWOPKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOD67AJOI#issuecomment-532546745>, or mute the thread<https://github.com/notifications/unsubscribe-auth/AI47XMEF4OIRJUQXF5V5KCDQKHF5HANCNFSM4IXXWOPA>.
|
@niartnelis did you figure out the data preprocessing part? and dataset format? |
Thank you very much! I think I can achieve it now. |
Can you tell me what does -1 means in wgt_ne and wgt_rel? |
Hi, could you share the pre-preprocessing code and data? THx |
Hi, Have you reproduce the pre-preprocessing code and data? |
Thanks for you reply!
My email is zhhhzhang@foxmail.com
…------------------ 原始邮件 ------------------
发件人: "LuoXukun"<notifications@github.com>;
发送时间: 2020年4月5日(星期天) 上午10:53
收件人: "tsujuifu/pytorch_graph-rel"<pytorch_graph-rel@noreply.github.com>;
抄送: "zhhhzhang"<zhhhzhang@foxmail.com>;"Comment"<comment@noreply.github.com>;
主题: Re: [tsujuifu/pytorch_graph-rel] code details (#6)
I am sorry that I havn't evaluate whether my reproduction is correct, and I will share it with you after I finish it.
------------------&nbsp;原始邮件&nbsp;------------------
发件人:&nbsp;"zhhhzhang"<notifications@github.com&gt;;
发送时间:&nbsp;2020年4月4日(星期六) 晚上10:58
收件人:&nbsp;"tsujuifu/pytorch_graph-rel"<pytorch_graph-rel@noreply.github.com&gt;;
抄送:&nbsp;"扭转乾坤"<861392914@qq.com&gt;;"Comment"<comment@noreply.github.com&gt;;
主题:&nbsp;Re: [tsujuifu/pytorch_graph-rel] code details (#6)
Hi, thanks for interested in my work.
Sorry for missing the pre-preprocessing code and data. (I left my previous lab and forgot to backup)
I will reproduce and update it later. (since I just start my PhD and it's quite busy these days, maybe after CVPR or ACL)
I try to clarify your problems here
for idx, inp, pos, dep_fw, dep_bw, ans_ne, wgt_ne, ans_rel, wgt_rel in ld_ts
BS: batch_size SL: sentence_length ED: embedding_dimension idx: not so important, you can just ignore it inp: the input sentence ([BS, SL, ED]) pos: the part-of-speech tag of each word ([BS, SL]) dep_fw: the dependencty adjacency matrix (forward edge) of each word-pair ([BS, SL, SL]) dep_bw: the dependencty adjacency matrix (backward edge) of each word-pair ([BS, SL, SL]) ans_ne, ans_rel: the output tag of name entity of each word and relation of each word-pair ([BS, SL] ans [BS, SL, SL]) wgt_ne, wgt_rel: the loss weight of name entity of each word and relation of each word-pair, 1 for those contains name entity or relation, otherwise 0 ([BS, SL], [BS, SL, SL])
pos is the part-of-speech tag of each word and it's from spaCy
the dependency parsing also comes from spaCy (please notice that there can be forward and backward edges of the dependency tree)
Hi, Have you reproduce the pre-preprocessing code and data?
Could you share it?
THx
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
你好,请问你复现了吗?我有个疑问,在第二阶段,GCN有num_rel个,相加会使得数值很大,会不会train飞了? |
没有呢,还没要到数据[捂脸] 你有数据么? 发一份呗
…------------------ 原始邮件 ------------------
发件人: "zhengnt"<notifications@github.com>;
发送时间: 2020年4月8日(星期三) 上午10:06
收件人: "tsujuifu/pytorch_graph-rel"<pytorch_graph-rel@noreply.github.com>;
抄送: "zhhhzhang"<zhhhzhang@foxmail.com>;"Comment"<comment@noreply.github.com>;
主题: Re: [tsujuifu/pytorch_graph-rel] code details (#6)
I am sorry that I havn't evaluate whether my reproduction is correct, and I will share it with you after I finish it.
…
------------------ 原始邮件 ------------------ 发件人: "zhhhzhang"<notifications@github.com>; 发送时间: 2020年4月4日(星期六) 晚上10:58 收件人: "tsujuifu/pytorch_graph-rel"<pytorch_graph-rel@noreply.github.com>; 抄送: "扭转乾坤"<861392914@qq.com>;"Comment"<comment@noreply.github.com>; 主题: Re: [tsujuifu/pytorch_graph-rel] code details (#6) Hi, thanks for interested in my work. Sorry for missing the pre-preprocessing code and data. (I left my previous lab and forgot to backup) I will reproduce and update it later. (since I just start my PhD and it's quite busy these days, maybe after CVPR or ACL) I try to clarify your problems here for idx, inp, pos, dep_fw, dep_bw, ans_ne, wgt_ne, ans_rel, wgt_rel in ld_ts BS: batch_size SL: sentence_length ED: embedding_dimension idx: not so important, you can just ignore it inp: the input sentence ([BS, SL, ED]) pos: the part-of-speech tag of each word ([BS, SL]) dep_fw: the dependencty adjacency matrix (forward edge) of each word-pair ([BS, SL, SL]) dep_bw: the dependencty adjacency matrix (backward edge) of each word-pair ([BS, SL, SL]) ans_ne, ans_rel: the output tag of name entity of each word and relation of each word-pair ([BS, SL] ans [BS, SL, SL]) wgt_ne, wgt_rel: the loss weight of name entity of each word and relation of each word-pair, 1 for those contains name entity or relation, otherwise 0 ([BS, SL], [BS, SL, SL]) pos is the part-of-speech tag of each word and it's from spaCy the dependency parsing also comes from spaCy (please notice that there can be forward and backward edges of the dependency tree) Hi, Have you reproduce the pre-preprocessing code and data? Could you share it? THx — You are receiving this because you commented. Reply to this email directly, view it on GitHub, or unsubscribe.
你好,请问你复现了吗?我有个疑问,在第二阶段,GCN有num_rel个,相加会使得数值很大,会不会train飞了?
—
You are receiving this because you commented.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
I have reproduced a dataset in JSON format with the following code, which is not guaranteed to be the same as the author's implementation. def tag_graphrel(self, relation_id_path, isTrain = True):
` def normalize_text(self, text):
` def find_all_index(self, sen_split, word_split): `
` def find_index(self, sen_split, word_split): `
` Note that: |
可否发一下这个预处理的完整代码,我看到这些代码是包含在一个类中的。我的邮箱605851710@qq.com 十分感谢! |
Can you share a complete code for me? I have bugs in using your code. I don't understand, thank you. If can, please 470294527@qq.com |
能否发一下这个预处理的完整代码,我的邮箱1979453046@qq.com 非常感谢! |
这就是我预处理的全部代码,经验证是可以跑通的,不行的话请自行debug。 |
还要吗
…---Original---
From: "Huang ***@***.***>
Date: Sat, Jan 29, 2022 18:10 PM
To: ***@***.***>;
Cc: ***@***.******@***.***>;
Subject: Re: [tsujuifu/pytorch_graph-rel] code details (#6)
***@***.***?谢谢!
—
Reply to this email directly, view it on GitHub, or unsubscribe.
Triage notifications on the go with GitHub Mobile for iOS or Android.
You are receiving this because you commented.Message ID: ***@***.***>
|
嗯嗯 |
I didn't get the data in pkl format, so I want to ask some details in the code:
1.dataloader:
for idx, inp, pos, dep_fw, dep_bw, ans_ne, wgt_ne, ans_rel, wgt_rel in ld_ts
what are the meanings of these variables?
2. pos is or not pre-characterized to the sentence.Is this part of speech tagging?
3. The adjacency matrix in the GCN should obtain the dependency of the related words. Is this the syntax dependency obtained by using the spacy?
The text was updated successfully, but these errors were encountered: